Hugging Face's logo

jhonalevc1995
/
deberta_large

Text Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
jhonalevc1995 commited on
Commit
6b18c97
·
verified ·
1 Parent(s): ba258cb

End of training

Browse files
Files changed (9) hide show
  1. README.md +117 -0
  2. added_tokens.json +3 -0
  3. config.json +35 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +15 -0
  6. spm.model +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +58 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/deberta-v3-large
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: deberta_large
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # deberta_large
16
+
17
+ This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.6965
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 3407
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 8
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_steps: 10
47
+ - num_epochs: 1
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:------:|:----:|:---------------:|
53
+ | 0.471 | 0.0173 | 20 | 0.2712 |
54
+ | 1.4977 | 0.0346 | 40 | 0.7702 |
55
+ | 0.7066 | 0.0519 | 60 | 0.4904 |
56
+ | 0.6817 | 0.0692 | 80 | 1.0408 |
57
+ | 0.897 | 0.0865 | 100 | 1.7531 |
58
+ | 0.6793 | 0.1039 | 120 | 0.8040 |
59
+ | 0.7946 | 0.1212 | 140 | 0.6972 |
60
+ | 0.7391 | 0.1385 | 160 | 0.6933 |
61
+ | 0.7441 | 0.1558 | 180 | 0.7431 |
62
+ | 0.656 | 0.1731 | 200 | 0.8636 |
63
+ | 0.5681 | 0.1904 | 220 | 0.7142 |
64
+ | 0.9031 | 0.2077 | 240 | 0.7183 |
65
+ | 0.5978 | 0.2250 | 260 | 0.7371 |
66
+ | 0.6308 | 0.2423 | 280 | 0.7036 |
67
+ | 0.6829 | 0.2596 | 300 | 0.6932 |
68
+ | 0.6472 | 0.2769 | 320 | 0.7010 |
69
+ | 0.6331 | 0.2942 | 340 | 0.7316 |
70
+ | 0.7698 | 0.3116 | 360 | 0.6938 |
71
+ | 0.6704 | 0.3289 | 380 | 0.7128 |
72
+ | 0.7532 | 0.3462 | 400 | 0.6992 |
73
+ | 0.703 | 0.3635 | 420 | 0.6932 |
74
+ | 0.7747 | 0.3808 | 440 | 0.7437 |
75
+ | 0.7063 | 0.3981 | 460 | 0.6931 |
76
+ | 0.6013 | 0.4154 | 480 | 0.7127 |
77
+ | 0.768 | 0.4327 | 500 | 0.6955 |
78
+ | 0.682 | 0.4500 | 520 | 0.6948 |
79
+ | 0.7419 | 0.4673 | 540 | 0.6976 |
80
+ | 0.6928 | 0.4846 | 560 | 0.6963 |
81
+ | 0.6246 | 0.5019 | 580 | 0.6995 |
82
+ | 0.6742 | 0.5193 | 600 | 0.6965 |
83
+ | 0.6419 | 0.5366 | 620 | 0.6947 |
84
+ | 0.7268 | 0.5539 | 640 | 0.6996 |
85
+ | 0.7054 | 0.5712 | 660 | 0.6938 |
86
+ | 0.6931 | 0.5885 | 680 | 0.7010 |
87
+ | 0.7344 | 0.6058 | 700 | 0.6975 |
88
+ | 0.7151 | 0.6231 | 720 | 0.6950 |
89
+ | 0.7106 | 0.6404 | 740 | 0.7027 |
90
+ | 0.6829 | 0.6577 | 760 | 0.6941 |
91
+ | 0.6883 | 0.6750 | 780 | 0.7005 |
92
+ | 0.6268 | 0.6923 | 800 | 0.6978 |
93
+ | 0.6674 | 0.7096 | 820 | 0.6979 |
94
+ | 0.6704 | 0.7270 | 840 | 0.7024 |
95
+ | 0.7527 | 0.7443 | 860 | 0.7010 |
96
+ | 0.7239 | 0.7616 | 880 | 0.7060 |
97
+ | 0.7611 | 0.7789 | 900 | 0.7033 |
98
+ | 0.7522 | 0.7962 | 920 | 0.7010 |
99
+ | 0.773 | 0.8135 | 940 | 0.6992 |
100
+ | 0.6564 | 0.8308 | 960 | 0.6959 |
101
+ | 0.7369 | 0.8481 | 980 | 0.6970 |
102
+ | 0.7119 | 0.8654 | 1000 | 0.6971 |
103
+ | 0.7181 | 0.8827 | 1020 | 0.6971 |
104
+ | 0.7011 | 0.9000 | 1040 | 0.6975 |
105
+ | 0.7414 | 0.9174 | 1060 | 0.6968 |
106
+ | 0.7732 | 0.9347 | 1080 | 0.6968 |
107
+ | 0.6499 | 0.9520 | 1100 | 0.6965 |
108
+ | 0.6681 | 0.9693 | 1120 | 0.6965 |
109
+ | 0.7831 | 0.9866 | 1140 | 0.6965 |
110
+
111
+
112
+ ### Framework versions
113
+
114
+ - Transformers 4.44.2
115
+ - Pytorch 2.4.1+cu121
116
+ - Datasets 3.0.1
117
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-large",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.44.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f1caa085d84c89ab64437f5c1d98ad0962f8792ec93a16c4397d5f8ff6806e
3
+ size 1740304440
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e7f7d5358a71fff2aa5a7102948ec09a641d54696e58beebba36e72c9ecdf9
3
+ size 5112